Conversation
github-actions
Bot
removed
the
action/benchmark
Contributor
Polar Signals Profiling ResultsLatest Run
Previous Runs (2)
Powered by Polar Signals Cloud |
Contributor
Benchmarks: PolarSignals ProfilingVortex (geomean): 1.123x ❌ datafusion / vortex-file-compressed (1.123x ❌, 0↑ 8↓)
|
Contributor
File Sizes: PolarSignals ProfilingNo file size changes detected. |
Merging this PR will not alter performance
|
Contributor
Benchmarks: FineWeb NVMeVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.895x ✅, 4↑ 4↓)
datafusion / vortex-compact (0.910x ➖, 1↑ 0↓)
datafusion / parquet (0.991x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.899x ✅, 3↑ 2↓)
duckdb / vortex-compact (0.886x ✅, 1↑ 0↓)
duckdb / parquet (0.967x ➖, 2↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: FineWeb NVMeNo file size changes detected. |
Contributor
Benchmarks: TPC-H SF=1 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.110x ❌, 0↑ 13↓)
datafusion / vortex-compact (1.125x ❌, 0↑ 14↓)
datafusion / parquet (1.068x ➖, 0↑ 8↓)
datafusion / arrow (1.132x ❌, 0↑ 15↓)
duckdb / vortex-file-compressed (1.117x ❌, 0↑ 12↓)
duckdb / vortex-compact (1.094x ➖, 0↑ 12↓)
duckdb / parquet (1.050x ➖, 0↑ 3↓)
duckdb / duckdb (1.085x ➖, 0↑ 8↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-H SF=1 on NVMENo file size changes detected. |
Contributor
Benchmarks: FineWeb S3Verdict: No clear signal (medium confidence) datafusion / vortex-file-compressed (0.803x ➖, 3↑ 3↓)
datafusion / vortex-compact (0.822x ➖, 3↑ 1↓)
datafusion / parquet (1.028x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.171x ➖, 1↑ 5↓)
duckdb / vortex-compact (0.942x ➖, 2↑ 3↓)
duckdb / parquet (0.989x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: Statistical and Population GeneticsVerdict: No clear signal (low confidence) duckdb / vortex-file-compressed (0.947x ➖, 3↑ 1↓)
duckdb / vortex-compact (0.938x ➖, 3↑ 0↓)
duckdb / parquet (0.914x ➖, 2↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: Statistical and Population GeneticsNo file size changes detected. |
Contributor
Benchmarks: TPC-H SF=10 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.074x ➖, 0↑ 4↓)
datafusion / vortex-compact (1.061x ➖, 0↑ 2↓)
datafusion / parquet (1.042x ➖, 0↑ 0↓)
datafusion / arrow (1.067x ➖, 0↑ 2↓)
duckdb / vortex-file-compressed (1.125x ❌, 0↑ 9↓)
duckdb / vortex-compact (1.089x ➖, 0↑ 6↓)
duckdb / parquet (1.014x ➖, 0↑ 0↓)
duckdb / duckdb (1.026x ➖, 0↑ 1↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-H SF=10 on NVMENo file size changes detected. |
Contributor
Benchmarks: TPC-H SF=1 on S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (1.187x ➖, 0↑ 6↓)
datafusion / vortex-compact (1.122x ➖, 0↑ 4↓)
datafusion / parquet (1.041x ➖, 0↑ 1↓)
duckdb / vortex-file-compressed (1.224x ➖, 0↑ 7↓)
duckdb / vortex-compact (1.217x ➖, 0↑ 10↓)
duckdb / parquet (0.992x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: Clickbench on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.056x ➖, 0↑ 6↓)
datafusion / parquet (1.029x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.077x ➖, 1↑ 8↓)
duckdb / parquet (1.006x ➖, 1↑ 0↓)
duckdb / duckdb (1.038x ➖, 0↑ 3↓)
Full attributed analysis
|
Contributor
File Sizes: Clickbench on NVMEFile Size Changes (1 files changed, -0.0% overall, 0↑ 1↓)
Totals:
|
Contributor
Benchmarks: TPC-DS SF=1 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.946x ➖, 7↑ 1↓)
datafusion / vortex-compact (0.956x ➖, 8↑ 0↓)
datafusion / parquet (0.939x ➖, 9↑ 0↓)
duckdb / vortex-file-compressed (0.964x ➖, 14↑ 5↓)
duckdb / vortex-compact (0.947x ➖, 14↑ 0↓)
duckdb / parquet (0.970x ➖, 6↑ 0↓)
duckdb / duckdb (0.942x ➖, 11↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-DS SF=1 on NVMENo file size changes detected. |
Contributor
Benchmarks: Random AccessVortex (geomean): 1.038x ➖ unknown / unknown (1.067x ➖, 0↑ 18↓)
|
Contributor
Benchmarks: CompressionVortex (geomean): 0.997x ➖ unknown / unknown (1.000x ➖, 6↑ 2↓)
|
Contributor
Benchmarks: TPC-H SF=10 on S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (1.123x ➖, 0↑ 6↓)
datafusion / vortex-compact (1.218x ➖, 0↑ 8↓)
datafusion / parquet (0.979x ➖, 0↑ 1↓)
duckdb / vortex-file-compressed (1.291x ➖, 0↑ 8↓)
duckdb / vortex-compact (1.325x ❌, 0↑ 11↓)
duckdb / parquet (0.924x ➖, 0↑ 0↓)
Full attributed analysis
|
a10y
reviewed
May 5, 2026
Comment on lines
+139
to
+141
| // Step 4: execute the projection only if the filter kept rows. | ||
| let reader = Arc::clone(&ctx.reader); | ||
| let projection = ctx.projection.clone(); |
a10y
approved these changes
May 5, 2026
Contributor
a10y
left a comment
a10y
left a comment
There was a problem hiding this comment.
looks good, definitely the change to task execution is good, i'm a bit confused where we actually cancel requests now?
a10y
requested changes
May 5, 2026
| } | ||
|
|
||
| let projection_future = | ||
| reader.projection_evaluation(&row_range, &projection, MaskFuture::ready(mask))?; |
Contributor
There was a problem hiding this comment.
actually, do we want to do this? different layouts should handle projection with empty Mask efficiently on their own I would hope? plus now we defer creating the projection_evaluation which kills some of the pre-fetching right?
Contributor
Author
There was a problem hiding this comment.
I don't think they actually do? For example, in flat layout we do:
let mut array = array.clone().await?;
let mask = mask.await?;
Contributor
|
I think this directionally makes sense, just want to make sure we wire in cancelation. This will probably fix a lot of issues we've had reported about Vortex doing a surprising amount of IO against S3. |
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
AdamGS
force-pushed
the
adamg/some-io-stuff
branch
from
7d02f45 to
b0c4fe8
Compare
github-actions
Bot
removed
the
action/benchmark
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Closes: #000
Testing